Update app.py

app.py

@@ -29,7 +29,7 @@ torch.backends.cudnn.allow_tf32 = False
 torch.backends.cudnn.deterministic = False
 #torch.backends.cudnn.benchmark = False
 torch.backends.cuda.preferred_blas_library="cublas"
-torch.backends.cuda.preferred_linalg_library="cusolver"
+#torch.backends.cuda.preferred_linalg_library="cusolver"
 
 torch.set_float32_matmul_precision("highest")
 
@@ -53,7 +53,7 @@ torch_dtype = torch.bfloat16
 
 checkpoint = "microsoft/Phi-3.5-mini-instruct"
 #vae = AutoencoderKL.from_pretrained("madebyollin/sdxl-vae-fp16-fix", torch_dtype=torch.float16)
-vae = AutoencoderKL.from_pretrained("ford442/sdxl-vae-bf16", torch_dtype=torch.bfloat16, device_map='balanced')
+vae = AutoencoderKL.from_pretrained("ford442/sdxl-vae-bf16", torch_dtype=torch.bfloat16)
 #vae = AutoencoderKL.from_pretrained("ford442/sdxl-vae-bf16")
 
 pipe = StableDiffusion3Pipeline.from_pretrained("ford442/stable-diffusion-3.5-medium-bf16", torch_dtype=torch.bfloat16).to(torch.device("cuda:0"))